k6-playwright-converter

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to include imports from jslib.k6.io (e.g., https://jslib.k6.io/k6-testing/latest/index.js) in generated scripts. These are official, well-known libraries maintained by the k6/Grafana community for performance testing utilities.
  • [COMMAND_EXECUTION]: The skill performs environment preparation using shell commands (mkdir -p k6/scripts) and executes generated scripts through a dedicated tool (mcp_k6_run_script). These operations are necessary for the skill's primary function of local script development and testing.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted user data (Playwright scripts) to generate executable code.
  • Ingestion points: User-supplied Playwright scripts are ingested in Step 1 for analysis and conversion.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the input scripts are defined.
  • Capability inventory: The skill possesses file-write capabilities (Step 6) and script execution capabilities via mcp_k6_run_script (Step 9).
  • Sanitization: No explicit sanitization or validation of the input script's content is mentioned beyond functional conversion logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 04:45 PM
Security Audit — agent-trust-hub — k6-playwright-converter